DETECTING PARKINSON'S DISEASE USING A STACKED LONG SHORT-TERM MEMORY DEEP NEURAL NETWORK WITH FEATURE FUSION

Abstract

Listen

Translate article

Parkinson's disease is a neurodegenerative disorder that affects millions of people worldwide. Early disease detection is crucial for effective treatment, but diagnosis can be challenging due to the subtle symptoms. This paper proposes a novel approach for Parkinson's disease detection using the SeaLion Method for feature extraction and the SL Deep NN model for classification. The SeaLion Method is used to extract features from time series data collected from Parkinson's disease patients and healthy individuals, and these features are used to train the SL Deep NN model. The model's performance is evaluated using accuracy, precision, recall, and F1 score metrics. Our results demonstrate that the SL Deep NN model can accurately classify time series data as belonging to a Parkinson's patient or a healthy individual. We use 10-fold cross-validation to evaluate the performance of each model and compare the results using metrics such as accuracy, precision, recall, and F1 score. Our results demonstrate that all four models achieve high accuracy, with the SVM model performing the best with an accuracy of over 95%. Our approach shows promise for developing a non-invasive, accurate, and automated method for Parkinson's disease detection, which could improve early diagnosis and treatment of the disease.